On a NO_HZ system, there may be an arbitrarily long delay between ticks on a CPU. When we're disabling ticks for a CPU, also disable the softlockup watchdog timer. Signed-off-by: Jeremy Fitzhardinge Cc: Ingo Molnar Cc: Thomas Gleixner Cc: john stultz Cc: Zachary Amsden Cc: James Morris Cc: Dan Hecht Cc: Paul Mackerras Cc: Martin Schwidefsky --- include/linux/sched.h | 8 ++++++++ kernel/softlockup.c | 23 +++++++++++++++++++---- kernel/time/tick-sched.c | 34 +++++++++++++++------------------- 3 files changed, 42 insertions(+), 23 deletions(-) =================================================================== --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -232,10 +232,18 @@ extern void scheduler_tick(void); #ifdef CONFIG_DETECT_SOFTLOCKUP extern void softlockup_tick(void); +extern void softlockup_enable(void); +extern void softlockup_disable(void); extern void spawn_softlockup_task(void); extern void touch_softlockup_watchdog(void); #else static inline void softlockup_tick(void) +{ +} +static inline void softlockup_enable(void) +{ +} +static inline void softlockup_disable(void) { } static inline void spawn_softlockup_task(void) =================================================================== --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -20,6 +20,7 @@ static DEFINE_PER_CPU(unsigned long long static DEFINE_PER_CPU(unsigned long long, touch_timestamp); static DEFINE_PER_CPU(unsigned long long, print_timestamp); static DEFINE_PER_CPU(struct task_struct *, watchdog_task); +static DEFINE_PER_CPU(int, enabled); static int did_panic = 0; @@ -41,6 +42,18 @@ void touch_softlockup_watchdog(void) } EXPORT_SYMBOL(touch_softlockup_watchdog); +void softlockup_enable(void) +{ + touch_softlockup_watchdog(); + wmb(); /* update timestamp before enable */ + __get_cpu_var(enabled) = 1; +} + +void softlockup_disable(void) +{ + __get_cpu_var(enabled) = 0; +} + /* * This callback runs from the timer interrupt, and checks * whether the watchdog thread has hung or not: @@ -51,8 +64,8 @@ void softlockup_tick(void) unsigned long long touch_timestamp = per_cpu(touch_timestamp, this_cpu); unsigned long long now; - /* watchdog task hasn't updated timestamp yet */ - if (touch_timestamp == 0) + /* return if not enabled */ + if (!__get_cpu_var(enabled)) return; /* report at most once a second */ @@ -95,8 +108,8 @@ static int watchdog(void * __bind_cpu) sched_setscheduler(current, SCHED_FIFO, ¶m); current->flags |= PF_NOFREEZE; - /* initialize timestamp */ - touch_softlockup_watchdog(); + /* enable on this cpu */ + softlockup_enable(); /* * Run briefly once per second to reset the softlockup timestamp. @@ -109,6 +122,8 @@ static int watchdog(void * __bind_cpu) touch_softlockup_watchdog(); schedule(); } + + softlockup_disable(); return 0; } =================================================================== --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -228,6 +228,8 @@ void tick_nohz_stop_sched_tick(void) ts->idle_tick = ts->sched_timer.expires; ts->tick_stopped = 1; ts->idle_jiffies = last_jiffies; + + softlockup_disable(); } /* * calculate the expiry time for the next timer wheel @@ -255,6 +257,7 @@ void tick_nohz_stop_sched_tick(void) cpu_clear(cpu, nohz_cpu_mask); } raise_softirq_irqoff(TIMER_SOFTIRQ); + out: ts->next_jiffies = next_jiffies; ts->last_jiffies = last_jiffies; @@ -311,6 +314,8 @@ void tick_nohz_restart_sched_tick(void) ts->tick_stopped = 0; hrtimer_cancel(&ts->sched_timer); ts->sched_timer.expires = ts->idle_tick; + + softlockup_enable(); while (1) { /* Forward the time to expire in the future */ @@ -355,17 +360,12 @@ static void tick_nohz_handler(struct clo tick_do_update_jiffies64(now); /* - * When we are idle and the tick is stopped, we have to touch - * the watchdog as we might not schedule for a really long - * time. This happens on complete idle SMP systems while - * waiting on the login prompt. We also increment the "start - * of idle" jiffy stamp so the idle accounting adjustment we - * do when we go busy again does not account too much ticks. - */ - if (ts->tick_stopped) { - touch_softlockup_watchdog(); + * Increment the "start of idle" jiffy stamp so the idle + * accounting adjustment we do when we go busy again does not + * account too much ticks. + */ + if (ts->tick_stopped) ts->idle_jiffies++; - } update_process_times(user_mode(regs)); profile_tick(CPU_PROFILING); @@ -450,17 +450,12 @@ static enum hrtimer_restart tick_sched_t */ if (regs) { /* - * When we are idle and the tick is stopped, we have to touch - * the watchdog as we might not schedule for a really long - * time. This happens on complete idle SMP systems while - * waiting on the login prompt. We also increment the "start of - * idle" jiffy stamp so the idle accounting adjustment we do - * when we go busy again does not account too much ticks. + * Increment the "start of idle" jiffy stamp so the + * idle accounting adjustment we do when we go busy + * again does not account too much ticks. */ - if (ts->tick_stopped) { - touch_softlockup_watchdog(); + if (ts->tick_stopped) ts->idle_jiffies++; - } /* * update_process_times() might take tasklist_lock, hence * drop the base lock. sched-tick hrtimers are per-CPU and @@ -522,6 +517,7 @@ void tick_cancel_sched_timer(int cpu) if (ts->sched_timer.base) hrtimer_cancel(&ts->sched_timer); ts->tick_stopped = 0; + softlockup_enable(); ts->nohz_mode = NOHZ_MODE_INACTIVE; } #endif /* HIGH_RES_TIMERS */ --